Method for managing an interface in a motor vehicle

Abstract

A method for managing at least one interface (41) in a motor vehicle (100), the interface (41) being configured to alert a driver of the motor vehicle (100) when a driving situation presents a level of risk exceeding a predetermined risk threshold (Sr), the method being characterized in that it comprises the following steps: - A step of collecting (E01) data representative of the complexity of a driving situation at a given time, in particular in real time; - A step of determining (E02, E03, E04, E05) a value representative of the complexity of the driving situation encountered; - A step of comparing (E06) the extracted value to a predetermined complexity threshold (Sc); - A step of inhibiting (E07) the at least one interface (41) as long as the value representative of the overall complexity of the driving situation encountered is greater than or equal to the predetermined complexity threshold.

Description

[0001] The invention relates to a method for managing an interface in a motor vehicle. The invention also relates to a driver assistance system for a motor vehicle, the driver assistance system implementing the aforementioned method. The invention further relates to a motor vehicle comprising such a driver assistance system. The invention further relates to a computer program implementing the aforementioned method. The invention also relates to a data storage medium on which such a program is stored. The invention further relates to a signal from such a data storage medium.

[0002] A driver of a motor vehicle is constantly faced with decisions related to the complexity of the driving situation encountered during their journey. It is therefore essential for the driver to have a comprehensive view of the driving situation in real time to assess its complexity, but also to understand how this complexity may evolve in the near future.

[0003] Generally speaking, the complexity of a driving situation refers to the number of factors and variables involved. These factors can affect the safety of the driver and / or those around them, particularly other road users. Various methods and devices exist to estimate the level of complexity of a situation. These methods and devices can be used to warn the driver through various interfaces to help them avoid taking risks.

[0004] However, when a driving situation becomes too complex, the flow of information communicated by the assistance system may disturb the driver, as their attention is then solicited from all sides, both by the driving situation encountered and by the warning messages sent by the interface(s).

[0005] The aim of the invention is to remedy the disadvantages described above by proposing a driver assistance system that makes it possible to assess the complexity of a driving situation, to predict the evolution of this complexity and to determine one or more types of driver assistance to warn the driver of said complexity, without cognitively overloading the driver when a complexity threshold is crossed.

[0006] To this end, the invention relates to a method for managing at least one interface in a motor vehicle, the interface being configured to alert a driver of the motor vehicle when a driving situation presents a level of risk exceeding a predetermined risk threshold, the method being characterized in that it comprises the following steps: A step of collecting data representative of the complexity of a driving situation at a given time, in particular in real time; A step of determining a value representative of the complexity of the driving situation encountered; A step of comparing the extracted value to a predetermined complexity threshold; A step of inhibiting at least one interface as long as the representative value of the overall complexity of the driving situation encountered is greater than or equal to the predetermined complexity threshold.

[0007] According to one embodiment, the step of determining a value representative of the complexity of the driving situation encountered includes: a step of classifying the data collected into at least two distinct categories, a step of assigning a complexity index to each category, a step of aggregating the complexity indices in a table, a step of extracting from said table a value representative of the overall complexity of the driving situation encountered.

[0008] According to one embodiment, the data collection step includes a substep in which a reliability index is assigned to the collected data.

[0009] According to one embodiment, data to which a reliability index lower than a threshold value has been assigned are excluded from the determination step.

[0010] According to one embodiment, the data collection step includes a substep of exchange with an accidentology database and during the data classification step, the information from said database is classified into a category specific to accidentology.

[0011] According to one embodiment, the step of assigning a complexity index to each category includes a substep of predicting the evolution of the overall complexity over a time horizon.

[0012] In one embodiment, the step of extracting a representative value of the overall complexity includes a substep of identifying the maximum value of the array components and / or a substep of calculating the average of the array components

[0013] According to one embodiment, the inhibition step includes a substep of recording in a local electronic memory data relating to a driving situation for which the level of complexity is greater than the predetermined threshold value for complexity.

[0014] The invention also relates to a driver assistance system for a motor vehicle, the system comprising hardware and / or software elements implementing the aforementioned method, in particular hardware and / or software elements designed to implement the aforementioned method.

[0015] In one embodiment, the hardware and / or software components of the driver assistance system include: a module for estimating the risk incurred for a driving situation encountered by the motor vehicle, a module for estimating the complexity of the driving situation, a module for managing at least one interface, and at least one interface, optionally, a local electronic memory.

[0016] According to one embodiment, the hardware and / or software components of the driver assistance system further include a situation prediction module configured to predict the driving situation for different time horizons.

[0017] The invention also relates to a motor vehicle characterized in that it includes a driver assistance system as described above.

[0018] The invention also relates to a computer program product comprising program code instructions recorded on a computer-readable medium to implement the steps of the process mentioned above when said program is running on a computer, or to a computer program product downloadable from a communication network and / or recorded on a data medium readable by a computer and / or executable by a computer, characterized in that it includes instructions which, when the program is executed by the computer, lead the computer to implement the process mentioned above.

[0019] The invention also relates to a computer-readable data recording medium on which is recorded a computer program comprising program code instructions for implementing the previously mentioned process, or to a computer-readable recording medium comprising instructions which, when executed by a computer, cause the computer to implement the previously mentioned process.

[0020] The invention also relates to a signal from a data carrier carrying the aforementioned computer program product.

[0021] These objects, features and advantages of the present invention will be described in detail in the following description of a particular embodiment, given by way of non-limiting example, with reference to the accompanying figures, among which: There [ Fig.1 ] schematically illustrates a driver assistance system according to the invention. The [ Fig.2 ] graphically illustrates the evolution of risk and complexity over time. The [ Fig.3 ] represents a flowchart of an execution method of a management process.

[0022] An example of a motor vehicle 100 equipped with an embodiment of a driver assistance system 10 is described below with reference to the [ Fig.1 ], done as a non-exhaustive list.

[0023] The driver assistance system 10 includes various means of perceiving the vehicle's environment 1, which may include all or some of the following means: means of observation 11 of the condition of the vehicle, and / or means of perception 12 of the environment close to the vehicle, and / or means of geolocation 13 of the vehicle, and / or means of communication 14 of the vehicle with road infrastructure and / or with other vehicles, and / or means 15 of internet connection.

[0024] The vehicle condition observation means 11 may include a means for observing an internal vehicle data network, for example, a CAN bus type network. The data transmitted via the internal data network may include, for example, instantaneous measurements of the vehicle's speed and / or acceleration and / or jerk, or the steering wheel angle and speed, the state of the brake or accelerator pedals, etc.

[0025] The means of perceiving the environment near the vehicle may include radars and / or lidars and / or cameras. Other embodiments of the perception means are conceivable.

[0026] The vehicle's geolocation means 13 may include a digital navigation map and data from a location system, such as GPS, allowing the driver to locate their vehicle on the digital navigation map and thus access information about the road network, including a topological and geometric description of the road network. This road network information may also include semantic information. For example, it may include the presence of a sign indicating a rule to be followed on a section of road (maximum speed, no overtaking), or a sign indicating the presence of a hazard (risk of animals, landslides, etc.).

[0027] The vehicle's communication capabilities with road infrastructure and / or other vehicles also allow for the retrieval of data on a set of objects perceived by road infrastructure equipment and / or other vehicles. This data includes, in particular, object classification data and their dimensions, position, and associated speeds.

[0028] The 15 means of internet connection also allow access to contextual data such as weather, road conditions and traffic conditions, etc.

[0029] When used by a driver, the motor vehicle 100 is required to move within a given environment. During these journeys, the driver of the motor vehicle 100 is likely to encounter various driving situations that involve a certain level of complexity.

[0030] Generally speaking, the overall complexity of a driving situation has both a static and a dynamic component. More specifically, the static component refers to static elements of the environment, such as road infrastructure and weather conditions, while the dynamic component refers to dynamic elements of the environment, such as other road users. Static complexity can be estimated well in advance, as the vehicle does not necessarily need to be present to provide the input data. Estimating dynamic complexity, on the other hand, requires the vehicle to be present at the location whose complexity is being assessed.

[0031] Regardless of the notion of complexity, the notion of risk must also be taken into account to assist a driver of a motor vehicle in their decision-making in the face of a driving situation.

[0032] In this context, the driver assistance system 10 of the vehicle 100 also includes a risk assessment module 2 for a given driving situation encountered by the driver of the motor vehicle. Based on data collected by the vehicle 100's environmental perception devices 1, the risk assessment module 2 can estimate the risk involved in a given driving situation. For example, it can evaluate the positions, speeds, and / or trajectories of other road users, detect the distance between the motor vehicle 100 and an object in its environment, and estimate the time remaining before a potential collision with that object. The risk assessment module 2 is also configured to predict how the risk will evolve over a time horizon. Here, "time horizon" refers to a predetermined time interval.For example, a time horizon for a prediction made by the risk estimation module 2 concerning the evolution of risk is between one and ten seconds.

[0033] The driver assistance system 10 also includes a complexity estimation module 3, this module 3 also receives the data collected by the various means of perception 1 and interprets them to extract the information relevant to estimating the complexity of the driving situation encountered by the driver of the motor vehicle 100.

[0034] To assist the driver in decision-making when faced with driving situations encountered on their journey, the motor vehicle 100 is generally equipped with one or more interfaces 41 configured to alert the driver of the motor vehicle 100 when a driving situation presents an excessively high level of risk. A high risk related to a driving situation can take many forms, such as excessive speed, insufficient distance between the vehicle and a surrounding obstacle, a slippery road surface, reduced visibility, etc.

[0035] Such an interface 41 is specifically configured to alert the driver via a warning method such as a visual one (flashing light, etc.) and / or an auditory one (emission of a sound of varying volume) and / or a haptic one (vibrating pedals, vibrating steering wheel, etc.) when a driving situation presents a risk level exceeding a predetermined risk threshold Sr. These warning methods can be combined. The intensity of the alert can depend on the level of risk involved and / or the time remaining before the vehicle collides with an obstacle.

[0036] To do this, the driver assistance system 10 includes an interface management module 4 which coordinates the interface(s) 41 present in the motor vehicle according to the estimated and predicted level of complexity and according to the estimated and predicted level of risk.

[0037] Within the framework of this invention, the risk level is not taken into account when assessing the complexity of a driving situation. However, the risk level is considered when estimating the optimal time to alert the driver, that is, the optimal time to activate one or more interfaces 41 via the interface management module 4 in order to send one or more alerts as appropriate. The risk level is also taken into account by the interface manager 4 when selecting the interface 41 to be used in the event of an alert.

[0038] An execution method for managing at least one interface 41 in a motor vehicle 1 is described below with reference to figures 2 And 3The process helps prevent cognitive overload for a driver of a motor vehicle when the complexity of a driving situation encountered by that driver is particularly high. The process is executed by the driver assistance system 10 of the motor vehicle. The process can therefore also be viewed as a method of operation of a driver assistance system or as a method of operation of a vehicle.

[0039] The first step, E01, of the process consists of collecting data representative of the complexity of a driving situation using the aforementioned perception tools 1. This data collection is carried out in real time by the perception tools 1, which then transmit this data to the complexity estimation module 3 and the risk estimation module 2.

[0040] Optionally, the method may include a substep E011 in which a reliability index is assigned to the collected data. This reliability index can be determined based on the consistency between data provided by a first perception means and a second perception means distinct from the first perception means. This substep E011 can be performed directly by the perception means 1, or more generally by the driver assistance system 10 of the motor vehicle.

[0041] The process then proceeds to a second classification step (E02) of the collected data into at least two distinct categories: a first category groups static elements, such as driving infrastructure present along a vehicle's route, while a second category groups dynamic elements, such as other road users. This classification can be performed by the complexity estimation module 3 in real time, or it can be performed beforehand.

[0042] The complexity estimation module 3 can be configured to classify data into more than two categories. In other words, the complexity estimation module 3 can offer multiple categories. Generally, a category groups elements that share common attributes. For example, one could define a category that groups road characteristics, listing data such as the number of lanes, direction of travel, etc. Another category could group characteristics related to potential interactions, such as the presence of intersections, bus lanes, cycle paths, pedestrian crossings, etc. A third category could group temporal factors, such as the date, time, outside temperature, or other meteorological elements.

[0043] Optionally, a category can be dedicated to accident analysis. In this optional embodiment, the first data collection step E01 includes a further exchange substep E012 with an accident analysis database. This exchange substep E012 with an accident analysis database is distinct from substep E011, during which a reliability index is assigned to the collected data. The exchange substep E012 with an accident analysis database is, for example, implemented before substep E011. During the implementation of the process, the information from this database is, for example, classified into a category specific to accident analysis during the second classification step E02.

[0044] Once the classification is complete, the process moves to a third step, E03, which assigns a complexity index to each category. This step is implemented by the complexity estimation module 3. The complexity index is a scalar that reflects the level of complexity associated with the elements present in the category. Specifically, it is strictly greater than zero and less than or equal to one. A low value for the complexity index reflects a relatively low level of complexity, while a high value reflects a higher level of complexity. The calculation of the complexity index for a category can be performed using a mathematical model or a neural network-type method, which can be based on machine learning.

[0045] If the system includes a specific category for accident statistics, the complexity index can be minimal if no accidents are recorded for the route, or at least a portion of the route taken by the motor vehicle. If one or more accidents are recorded in a database for the route, or at least a portion of the route taken by the motor vehicle, the complexity index can vary depending on factors such as the date the accident occurred, its severity, or other attributes.

[0046] Once a complexity index has been assigned to each of the categories considered, the process proceeds to a fourth step, E04, which aggregates the complexity indices into a table. This table can, for example, take the form of a column where the number of rows corresponds to the number of categories considered. Such a representation of the calculated complexity indices facilitates the identification of the main source(s) of complexity, which can impact the type of warning and / or the type of interface chosen to alert the driver, if necessary. The fourth step, E04, of aggregating the complexity indices into a table is implemented, in particular, by the complexity estimation module 3.

[0047] In cases where the first data collection step E01 of the process includes substep E011 during which a reliability index is assigned to the collected data, data to which a reliability index below a threshold value has been assigned are excluded from the fourth aggregation step E04. In this way, outliers and / or obsolete data are not taken into account in the complexity assessment.

[0048] The third assignment step E03 of the process may include a substep E031 for predicting the evolution of complexity over a time horizon. The time horizon for predicting the evolution of dynamic complexity is shorter than the time horizon for predicting the evolution of static complexity. More precisely, using data collected in real time and data already available but relating to a future event, a prediction of the evolution of complexity can be established in the short term (a few seconds to a few minutes), or even in the medium term (a few tens of minutes to a few hours, for example, two hours). The prediction of the evolution of complexity in the short term can take into account both static and dynamic complexity.On the other hand, predicting the evolution of long-term complexity can only take into account static complexity, since data concerning dynamic complexity will only be present from the moment the vehicle is present on site.

[0049] During this E031 prediction substep of complexity evolution, the previously mentioned table can be supplemented with additional columns: each column then represents a distinct time point. The first column of the table lists the complexity indices of the different categories calculated in real time for a time t0, the second column lists the complexity indices for these same categories for a time t0+Δt, the third column lists the complexity indices for these same categories for a time t0+2*Δt, and so on.

[0050] According to one embodiment, the driver assistance system 10 may include a situation prediction module 31. The situation prediction module 31 is configured to predict the driving situation for different time horizons, and then the complexity estimation module 3 estimates the complexity for each of these time horizons. In this embodiment, the situation prediction module 31 and the complexity estimation module 3 are coordinated to jointly execute the prediction substep E031.

[0051] The E031 prediction sub-step may use one or more mathematical methods which, based on previously collected data, can estimate the evolution of the complexity of road situations that the driver of the motor vehicle will soon encounter.

[0052] The process then proceeds to a fifth extraction step, E05, of a value representative of the overall complexity of the driving situation encountered by the driver at a given moment, particularly in real time. This fifth extraction step, E05, can be performed by the complexity estimation module 3.

[0053] In one embodiment, this fifth step, E05, of extracting a representative value of the overall complexity, includes a substep E051 of identifying the maximum value of the array components. This substep E051 then consists of identifying the complexity index with the highest value in the array.

[0054] In addition, or alternatively, the fifth extraction step E05 of a representative value of the overall complexity can include a calculation substep E052 of the average of the array components. This substep E052 consists, for example, of calculating a weighted average of the array components. Other methods, including mathematical methods, can be considered to extract at least one representative value of the overall complexity from the array.

[0055] The second, third, fourth, fifth steps E02, E03, E04, E05, and possibly sub-step E031 together constitute a step for determining a value representative of the complexity of the driving situation encountered.

[0056] The process then proceeds to a sixth step, E06, which compares the extracted value to a predetermined complexity threshold, Sc. This predetermined complexity threshold, Sc, is, for example, a scalar. Specifically, it is strictly greater than zero and less than or equal to one. This predetermined complexity threshold, Sc, represents a level of complexity that demands a significant portion of the driver's attention. Beyond this threshold, any distraction requiring the driver's attention is undesirable. The sixth step, E06, which compares the extracted value to a predetermined complexity threshold, Sc, can be implemented by the complexity estimation module 3.

[0057] As long as the representative value of the overall complexity of the driving situation encountered by the motorist is less than the predetermined complexity threshold Sc, the interface(s) 41 can be activated by the interface management module 4 to warn the driver of an imminent risk and / or an increase in the complexity of the driving situation in the near future.

[0058] However, as soon as this representative value of overall complexity is greater than or equal to the predetermined complexity threshold Sc, the process proceeds to a seventh step E07 during which the interface(s) 41 in the motor vehicle are inhibited. This seventh inhibition step E07 is implemented by the interface management module 4. In particular, the interface management module 4 does not activate the interface(s) 41 as long as the representative value of overall complexity is greater than or equal to the predetermined complexity threshold Sc. Thus, when the overall complexity of a driving situation is too high, the interface(s) 41 no longer engage the driver, regardless of the level of risk associated with the driving situation encountered, in order to avoid cognitively overloading the driver.

[0059] According to a preferred embodiment, the seventh inhibition step E07 of at least one interface 41 includes a substep of recording E071 in a local electronic memory 5 of data relating to a driving situation for which the level of complexity is greater than the predetermined threshold value Sc for complexity.

[0060] In this preferred embodiment, the driver assistance system 10 includes a local electronic memory 5 configured to perform the recording substep E071 mentioned previously. The data recorded in the local electronic memory 5 may, for example, be images and / or geolocation data. This data may be time-stamped and / or geolocated. The local electronic memory 5 can be queried by the driver when cognitively available. The driver assistance system 10 can then retrieve the data recorded in the local electronic memory 5 and present it to the driver, notably via at least one interface 41. The driver assistance system 10 can also provide explanations about the risks involved at the time of the recorded situation and / or the complexity encountered.The driver assistance system 10 can, for example, provide the driver with advice on how to limit risk-taking in similar situations and / or suggest alternative behaviors to those adopted by the driver when the situation occurred in order to avoid an increase in risk in similar situations in the future.

[0061] There [ Fig.2 ] graphically illustrates an example of how the level of complexity and the evolution of risk change over time. On this [ Fig.2 ], a first horizontal line represents the predetermined threshold value Sr for risk and a second horizontal line, located above the first horizontal line, represents the predetermined threshold value Sc for complexity. On this same [ Fig.2 ], a solid line curve represents the evolution over time of the representative value of the overall complexity of the driving situation encountered; and a dotted line curve represents the evolution of the level of risk over time.

[0062] During the initial period P1, the estimated risk for the driving situation is significantly lower than the predetermined risk threshold Sr, therefore there is no need to send an alert to the driver via one or more interfaces 41. In this same period P1, the calculated complexity exceeds the predetermined complexity threshold Sc, and the interface(s) 41 are therefore inhibited: no alert is sent to the driver to avoid cognitive overload as long as the representative value of the overall complexity of the driving situation encountered by the driver remains above the predetermined complexity threshold Sc. It should be noted, however, that towards the end of the initial period P1, the level of complexity gradually decreases, while the risk level increases, although it remains below the predetermined risk threshold Sr.

[0063] When the calculated complexity falls below the predetermined threshold value Sc, the vehicle's interface(s) 41 are no longer inhibited, marking the beginning of period P2. During this second period P2, the representative values ​​of the overall complexity calculated by the complexity estimation module 3 remain below the predetermined threshold value for complexity, as does the risk level estimated by the risk estimation module 2; the estimated risk level remains below the predetermined threshold value Sr for risk. It should be noted, however, that towards the end of the second period P2, the risk level increases quite rapidly. The interface(s) 41 can then be used to send alerts to the driver, notably to warn them of the increased risk.

[0064] When the risk level exceeds the predetermined threshold value, a third period P3 begins, during which one or more alerts are sent to the driver via one or more interfaces 41. The risk level is taken into account by the interface manager 4 when selecting the interface 41 used to alert the driver. The intensity of the alerts may increase as the risk level continues to rise during this third period P3. During this period P3, the level of complexity gradually decreases and reaches a minimum value at the end of the period P3.

[0065] A fourth period, P4, begins when the risk level, although high, starts to plateau before gradually decreasing until it reaches the predetermined threshold value, Sr, for the risk. During this period, P4, the interface management module 4 continues to manage the interface(s) to alert the driver; however, the frequency and / or intensity of the alerts may decrease, mirroring the risk level estimated by the risk estimation module 2. During this fourth period, P4, the level of complexity increases while remaining below the predetermined threshold value for complexity.

[0066] A fifth period, P5, begins when the risk level falls below the predetermined threshold value, Sr, for risk. During this period, P5, the complexity level continues to increase until it reaches the predetermined threshold value, Sc, for complexity. During this period, the interface management module 4 can manage interface(s) 41 to alert the driver to the increasing complexity.

[0067] The beginning of the last period P6 of the example illustrated on this [ Fig.2 ] is marked by the level of complexity which exceeds the predetermined threshold value Sc for complexity: the interface(s) 41 are again inhibited.

[0068] One can also consider a case not illustrated on the [ Fig.2[ ], case in which both the complexity level and the risk level are above their respective threshold values. In this particular case, interface(s) 41 are inhibited: no alert is sent to the driver to avoid cognitive overload as long as the representative value of the overall complexity of the driving situation encountered by the driver remains above the predetermined complexity threshold Sc, despite the risk level also being high and, in particular, above the predetermined threshold value Sr for risk.

[0069] In a preferred embodiment, the driver assistance system 10 has access to one or more databases. The driver assistance system 10 includes, for example, communication means configured to query the database(s) and receive responses. These communication means can also be configured to exchange data between the database and the driver assistance system 10, in particular to update the data contained in the database.

Claims

1. A method for managing at least one interface (41) in a motor vehicle (100), the interface (41) being configured to alert a driver of the motor vehicle (100) when a driving situation presents a risk level exceeding a predetermined risk threshold (Sr), the method being characterized in that It includes the following steps: - A collection step (E01) of data representative of the complexity of a driving situation at a given time, in particular in real time; - A determination step (E02, E03, E04, E05) of a value representative of the complexity of the driving situation encountered; - A comparison step (E06) of the extracted value to a predetermined complexity threshold (Sc); - A inhibition step (E07) of at least one interface (41) as long as the representative value of the overall complexity of the driving situation encountered is greater than or equal to the predetermined complexity threshold (Sc).

2. Method according to the preceding claim, characterized in that The step of determining (E02, E03, E04, E05) a value representative of the complexity of the driving situation encountered includes: - a step of classifying (E02) the data collected into at least two distinct categories, - a step of assigning (E03) a complexity index to each category, - a step of aggregating (E04) the complexity indices in a table, - a step of extracting (E05) from said table a value representative of the overall complexity of the driving situation encountered.

3. A method according to any one of the preceding claims, characterized in that The data collection step (E01) includes a substep (E011) during which a reliability index is assigned to the collected data.

4. Method according to the preceding claim, characterized in thatData to which a reliability index below a threshold value has been assigned are excluded from the determination step (E02, E03, E04, E05).

5. A method according to any one of the preceding claims, characterized in that The data collection step (E01) includes a sub-step of exchange (E012) with an accident database and in that During the data classification stage (E02), the information from said database is classified into a category specific to accidentology.

6. A method according to any one of the preceding claims and claim 2, characterized in that The step of assigning (E03) a complexity index to each category includes a sub-step of predicting (E031) the evolution of the overall complexity over a time horizon.

7. A method according to any one of the preceding claims and claim 2, characterized in thatThe extraction step (E05) of a representative value of the overall complexity includes a sub-step of identification (E051) of the maximum value of the components of the table and / or a sub-step of calculation (E052) of the average of the components of the table.

8. A method according to any one of the preceding claims, characterized in that The inhibition step (E07) includes a substep of recording (E071) in a local electronic memory (5) data relating to a driving situation for which the level of complexity is greater than the predetermined threshold value (Sc) for complexity.

9. Driver assistance system (10) for a motor vehicle, the system comprising hardware (2, 3, 4) and / or software elements implementing the method according to any one of claims 1 to 8, in particular hardware (2, 3, 4) and / or software elements designed to implement the method according to any one of the preceding claims.

10. Driver assistance system (10) according to the preceding claim, characterized in that The hardware and / or software elements (2, 3, 4) include: - a risk estimation module (2) for a driving situation encountered by the motor vehicle, - a complexity estimation module (3) for the driving situation, - a management module (4) for at least one interface (41), and - at least one interface (41), - optionally, a local electronic memory (5).

11. Driver assistance system (10) according to claim 9 or 10, characterized in that the hardware and / or software elements (2, 3, 4, 5) further include a situation prediction module (31) configured to predict the driving situation for different time horizons.

12. Motor vehicle characterized in that It includes a driver assistance system (10) according to any one of claims 9 to 11.

13. Product computer program comprising program code instructions recorded on a computer-readable medium to implement the steps of the process according to any one of claims 1 to 8 when said program runs on a computer or product computer program downloadable from a communication network and / or recorded on a computer-readable data medium and / or executable by a computer, characterized in that it comprises instructions which, when the program is executed by the computer, cause the computer to implement the process according to any one of claims 1 to 8.

14. Computer-readable data recording medium on which is recorded a computer program comprising program code instructions for implementing the process according to any one of claims 1 to 8, or computer-readable recording medium comprising instructions which, when executed by a computer, cause the computer to implement the process according to any one of claims 1 to 8.

15. Signal from a data carrier, carrying the computer program product according to claim 13.

Images